© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58791
    Prev
    Next
    INDEX
    Explanations

    Oreo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éħį
    -0.12
     Packing
    -0.10
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.10
     packing
    -0.10
    packing
    -0.10
    åīįä¸ī
    -0.09
    ç»¿åľ°
    -0.09
    packed
    -0.08
     METH
    -0.08
    _restrict
    -0.08
    POSITIVE LOGITS
    人å¿ĥ
    0.11
    éľ¹
    0.10
     WX
    0.10
    æ°ijå¿ĥ
    0.10
    离
    0.10
    åĩī
    0.09
    åĬĿ
    0.09
    宽
    0.09
     Cabr
    0.09
    éĽ¢
    0.09
    Activations Density 0.007%

    No Known Activations